Remote RAG Data Engineer: OpenSearch & Embeddings Expert

Booz Allen; Fort Meade (MD); On-site; USD 62,000 - 141,000; Full time

Benefits offered by this job

Health benefits

Retirement benefits

Paid leave

Professional development

Tuition assistance

Work-life programs

Dependent care

Job summary

Booz Allen Hamilton in Fort Meade, MD seeks a RAG Data Engineer to build and operate the data ingestion and search infrastructure powering Retrieval-Augmented Generation capabilities. You will own ingestion, embedding, and indexing workflows, connecting enterprise data with Amazon Bedrock and OpenSearch, and optimizing performance.

You will collaborate with cloud architects, security engineers, application developers, and AI/ML specialists to establish a scalable, secure data retrieval

Qualifications

• ETL and data ingestion pipelines for structured and unstructured data.
• Document normalization, parsing, chunking, content preparation workflows, and embeddings integration.
• OpenSearch/Elasticsearch indexes, schemas, mappings, and aliases design and tuning.
• Idempotent ingestion processes with upsert, delete, replay, and recovery.
• Metadata modeling, enrichment, lineage, and version tracking.
• Python or other data engineering languages.
• Containerized deployment with Docker/ECS/EKS/Kubernetes.

Responsibilities

• Build and operate the data ingestion and search infrastructure powering RAG capabilities.
• Own ingestion, embedding, and indexing workflows connecting enterprise data with Bedrock and OpenSearch.
• Design and optimize OpenSearch indexes, mappings, shard configurations, lifetime policies, and query performance.
• Ensure idempotent ingestion with upsert/delete/replay and recovery mechanisms.
• Collaborate with cloud architects, security engineers, developers, and AI/ML teams to ensure scalable, secure data foundations.

Skills

ETL pipelines

Python

Data ingestion

Metadata modeling

Search design

Collaboration

Cloud collaboration

Security awareness

Education

HS diploma or GED

Tools

Docker

ECS

EKS

Kubernetes

OpenSearch/Elasticsearch

Spark

Ray

Dask

Kafka

SQS

Terraform

CloudFormation

AWS CDK

Amazon Bedrock

Job description

Booz Allen Hamilton in Fort Meade, MD seeks a RAG Data Engineer to build and operate the data ingestion and search infrastructure powering Retrieval-Augmented Generation capabilities. You will own ingestion, embedding, and indexing workflows, connecting enterprise data with Amazon Bedrock and OpenSearch, and optimizing performance.

You will collaborate with cloud architects, security engineers, application developers, and AI/ML specialists to establish a scalable, secure data retrieval